A scene-graph-to-image model that refines object boxes using each relationship separately, then generates images with a three-stage GAN, reports improved layout accuracy and image quality on COCO-Stuff and Visual Genome.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Visual-Relation Conscious Image Generation from Structured-Text
A scene-graph-to-image model that refines object boxes using each relationship separately, then generates images with a three-stage GAN, reports improved layout accuracy and image quality on COCO-Stuff and Visual Genome.